Sanitized Evidence Pack
Proof Pack
Public evidence for AI application product, Agent workflow, LLM Eval, trace/replay, and business delivery. This page shows recruiter-safe artifacts only; raw logs, private dashboards, application strategy, and credentials stay private.
Evidence map
Case Pages
Each case states what it proves, the workflow behind it, visible evidence, safe boundaries, and which role families it supports.
Curvature, rhythm, and local equilibrium instead of enclosure.
Multimodal Workflow
Meeting Workflow
A runnable meeting review workflow that turns audio, screen material, images, and documents into a traceable workbench.
Developer Experience
AI Coding Trace
A local trace viewer that converts Codex and Claude Code JSONL sessions into redacted context and token visualizations.
LLM Eval
NIH Text Evaluation
A text-evaluation workflow for NIH-style project material, focused on rubric, data scope, badcase review, bias awareness, and human review.
Business Delivery
Guanlan Digitization
A real business delivery case covering ERP-style data management, WeChat Mini Program, website structure, and handoff materials.
External Signals
Awards and Recognition
Selected honors that support the industrial AI, sustainability, and engineering-practice parts of the resume.
Boundary
The public version intentionally excludes raw conversations, private logs, hidden dashboards, application queues, salary strategy, and customer-sensitive data. Deeper material can be discussed in interviews when appropriate.